Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to possessive forms or possessive nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fillType
    -0.51
     createState
    -0.51
    GOTREF
    -0.50
     незавершена
    -0.49
    retudo
    -0.48
    expectedResult
    -0.46
     ModelAndView
    -0.45
    tagHelperRunner
    -0.44
    AnimationsModule
    -0.44
    DropTable
    -0.43
    POSITIVE LOGITS
    ⓧ
    0.47
     itself
    0.47
     its
    0.42
     ưu
    0.40
    它的
    0.40
     ajudá
    0.40
     Itself
    0.40
    Története
    0.39
     robustness
    0.39
     quirks
    0.39
    Act Density 0.043%

    No Known Activations